ltc-code 0.1.5__tar.gz → 0.1.6__tar.gz

{ltc_code-0.1.5 → ltc_code-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.1.5
+Version: 0.1.6
 Summary: Add your description here
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown

{ltc_code-0.1.5 → ltc_code-0.1.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.1.5"
+version = "0.1.6"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

{ltc_code-0.1.5 → ltc_code-0.1.6}/src/ltc_code/may27.py

@@ -1713,35 +1713,22 @@ def lookup_sid_cepr(
 ) -> Frame:
 
     is_lazy = isinstance(frame, pl.LazyFrame)
+    current = frame.collect() if is_lazy else frame
 
-    current = (
-        frame.collect()
-        if is_lazy
-        else frame
+    current = current.with_columns(
+        *clean_name(cols["fname"]),
+        *clean_name(cols["lname"]),
+        *clean_dob(col=cols["dob"]),
     )
 
-    #
-    # CLEAN LEFT SIDE
-    #
-
-    current = (
-        current
-        .with_columns(
-            *clean_name(cols["fname"]),
-            *clean_name(cols["lname"]),
-            *clean_dob(col=cols["dob"]),
-        )
+    current = current.with_columns(
+        _parse_dob_expr(f"{cols['dob']}_clean").alias(f"{cols['dob']}_clean")
     )
 
     matched_frames = []
-
     unmatched = current
 
-    #
-    # STAGE 1
-    # EXACT
-    #
-
+    # exact
     matched, unmatched = _run_match_stage(
         unmatched,
         lookup=lookups["exact"],
@@ -1750,91 +1737,173 @@ def lookup_sid_cepr(
         dob_expr=pl.col(f"{cols['dob']}_clean"),
         label="exact",
     )
-
     matched_frames.append(matched)
 
-    #
-    # STAGE 2
-    # MNAME
-    #
-
+    # middle-name variants
     if "mname" in cols:
-
-        unmatched = (
-            unmatched
-            .with_columns(
-                *clean_other_name(cols["mname"])
-            )
+        unmatched = unmatched.with_columns(
+            *clean_other_name(cols["mname"])
         )
 
-        matched, unmatched = _run_match_stage(
-            unmatched,
-            lookup=lookups["mname"],
-            fname_expr=pl.concat_str(
-                [
-                    pl.col(f"{cols['fname']}_clean"),
-                    pl.col(f"{cols['mname']}_clean"),
-                ],
-                separator=" ",
+        mname_stages = [
+            (
+                "left exact -> right fname + mname",
+                lookups["mname"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.col(f"{cols['lname']}_clean"),
             ),
-            lname_expr=pl.col(f"{cols['lname']}_clean"),
-            dob_expr=pl.col(f"{cols['dob']}_clean"),
-            label="mname",
-        )
-
-        matched_frames.append(matched)
+            (
+                "left exact -> right mname + lname",
+                lookups["mname_lname"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left exact -> right fname + mname no space",
+                lookups["mname_nospace"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left fname + mname -> right exact",
+                lookups["exact"],
+                pl.concat_str(
+                    [pl.col(f"{cols['fname']}_clean"), pl.col(f"{cols['mname']}_clean")],
+                    separator=" ",
+                ),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left mname + lname -> right exact",
+                lookups["exact"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.concat_str(
+                    [pl.col(f"{cols['mname']}_clean"), pl.col(f"{cols['lname']}_clean")],
+                    separator=" ",
+                ),
+            ),
+            (
+                "left fname + mname no space -> right exact",
+                lookups["exact"],
+                pl.concat_str(
+                    [pl.col(f"{cols['fname']}_clean"), pl.col(f"{cols['mname']}_clean")],
+                    separator="",
+                ),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+        ]
 
-    #
-    # STAGE 3
-    # SUFFIX
-    #
+        for label, lookup, fname_expr, lname_expr in mname_stages:
+            matched, unmatched = _run_match_stage(
+                unmatched,
+                lookup=lookup,
+                fname_expr=fname_expr,
+                lname_expr=lname_expr,
+                dob_expr=pl.col(f"{cols['dob']}_clean"),
+                label=label,
+            )
+            matched_frames.append(matched)
 
+    # suffix variants
     if "suffix" in cols:
+        unmatched = unmatched.with_columns(
+            *clean_other_name(cols["suffix"])
+        )
 
-        unmatched = (
-            unmatched
-            .with_columns(
-                *clean_other_name(cols["suffix"])
+        suffix_stages = [
+            (
+                "left exact -> right lname + suffix",
+                lookups["suffix"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left exact -> right fname + suffix",
+                lookups["suffix_fname"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left exact -> right fname + suffix no space",
+                lookups["suffix_fname_nospace"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left exact -> right lname + suffix no space",
+                lookups["suffix_lname_nospace"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left fname + suffix -> right exact",
+                lookups["exact"],
+                pl.concat_str(
+                    [pl.col(f"{cols['fname']}_clean"), pl.col(f"{cols['suffix']}_clean")],
+                    separator=" ",
+                ),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left fname + suffix no space -> right exact",
+                lookups["exact"],
+                pl.concat_str(
+                    [pl.col(f"{cols['fname']}_clean"), pl.col(f"{cols['suffix']}_clean")],
+                    separator="",
+                ),
+                pl.col(f"{cols['lname']}_clean"),
+            ),
+            (
+                "left lname + suffix -> right exact",
+                lookups["exact"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.concat_str(
+                    [pl.col(f"{cols['lname']}_clean"), pl.col(f"{cols['suffix']}_clean")],
+                    separator=" ",
+                ),
+            ),
+            (
+                "left lname + suffix no space -> right exact",
+                lookups["exact"],
+                pl.col(f"{cols['fname']}_clean"),
+                pl.concat_str(
+                    [pl.col(f"{cols['lname']}_clean"), pl.col(f"{cols['suffix']}_clean")],
+                    separator="",
+                ),
+            ),
+        ]
+
+        for label, lookup, fname_expr, lname_expr in suffix_stages:
+            matched, unmatched = _run_match_stage(
+                unmatched,
+                lookup=lookup,
+                fname_expr=fname_expr,
+                lname_expr=lname_expr,
+                dob_expr=pl.col(f"{cols['dob']}_clean"),
+                label=label,
             )
-        )
+            matched_frames.append(matched)
+
+    # dob_imp variants
+    dob_imp_stages = [
+        "dob_imp",
+        "dob_imp_minus_1",
+        "dob_imp_plus_1",
+        "dob_imp_minus_2",
+        "dob_imp_plus_2",
+    ]
 
+    for key in dob_imp_stages:
         matched, unmatched = _run_match_stage(
             unmatched,
-            lookup=lookups["suffix"],
+            lookup=lookups[key],
             fname_expr=pl.col(f"{cols['fname']}_clean"),
-            lname_expr=pl.concat_str(
-                [
-                    pl.col(f"{cols['lname']}_clean"),
-                    pl.col(f"{cols['suffix']}_clean"),
-                ],
-                separator=" ",
-            ),
+            lname_expr=pl.col(f"{cols['lname']}_clean"),
             dob_expr=pl.col(f"{cols['dob']}_clean"),
-            label="suffix",
+            label=key,
         )
-
         matched_frames.append(matched)
 
-    #
-    # STAGE 4
-    # DOB IMP
-    #
-
-    matched, unmatched = _run_match_stage(
-        unmatched,
-        lookup=lookups["dob_imp"],
-        fname_expr=pl.col(f"{cols['fname']}_clean"),
-        lname_expr=pl.col(f"{cols['lname']}_clean"),
-        dob_expr=pl.col(f"{cols['dob']}_clean"),
-        label="dob_imp",
-    )
-
-    matched_frames.append(matched)
-
-    #
-    # FINAL
-    #
-
     result = pl.concat(
         matched_frames + [unmatched],
         how="diagonal_relaxed",